CN108415898B - 深度学习语言模型的词图重打分方法和*** - Google Patents
深度学习语言模型的词图重打分方法和*** Download PDFInfo
- Publication number
- CN108415898B CN108415898B CN201810054749.2A CN201810054749A CN108415898B CN 108415898 B CN108415898 B CN 108415898B CN 201810054749 A CN201810054749 A CN 201810054749A CN 108415898 B CN108415898 B CN 108415898B
- Authority
- CN
- China
- Prior art keywords
- word
- sequence
- node
- language model
- words
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000013135 deep learning Methods 0.000 title claims abstract description 50
- 238000013077 scoring method Methods 0.000 title claims description 17
- 238000000034 method Methods 0.000 claims abstract description 43
- 238000004364 calculation method Methods 0.000 claims abstract description 31
- 230000015654 memory Effects 0.000 claims abstract description 12
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000013138 pruning Methods 0.000 abstract description 53
- 238000002474 experimental method Methods 0.000 description 35
- 238000013528 artificial neural network Methods 0.000 description 22
- 238000004422 calculation algorithm Methods 0.000 description 22
- 238000010586 diagram Methods 0.000 description 17
- 238000005457 optimization Methods 0.000 description 11
- 230000001133 acceleration Effects 0.000 description 9
- 238000012549 training Methods 0.000 description 9
- 239000013598 vector Substances 0.000 description 9
- 230000000694 effects Effects 0.000 description 7
- 238000012360 testing method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000002776 aggregation Effects 0.000 description 5
- 238000004220 aggregation Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000012217 deletion Methods 0.000 description 3
- 230000037430 deletion Effects 0.000 description 3
- 230000000052 comparative effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011056 performance test Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/355—Class or cluster creation or modification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Machine Translation (AREA)
Abstract
Description
语言模型 | eval2000 | eval_rt03s |
3-gram | 107.18 | 96.18 |
4-gram | 76.28 | 62.45 |
LSTM | 58.73 | 44.99 |
Claims (9)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810054749.2A CN108415898B (zh) | 2018-01-19 | 2018-01-19 | 深度学习语言模型的词图重打分方法和*** |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810054749.2A CN108415898B (zh) | 2018-01-19 | 2018-01-19 | 深度学习语言模型的词图重打分方法和*** |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108415898A CN108415898A (zh) | 2018-08-17 |
CN108415898B true CN108415898B (zh) | 2021-09-24 |
Family
ID=63125790
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810054749.2A Active CN108415898B (zh) | 2018-01-19 | 2018-01-19 | 深度学习语言模型的词图重打分方法和*** |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108415898B (zh) |
Families Citing this family (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109710087B (zh) * | 2018-12-28 | 2023-01-13 | 北京金山安全软件有限公司 | 输入法模型生成方法及装置 |
US11151332B2 (en) * | 2019-03-07 | 2021-10-19 | International Business Machines Business | Dialog based speech recognition |
CN112071310B (zh) * | 2019-06-11 | 2024-05-07 | 北京地平线机器人技术研发有限公司 | 语音识别方法和装置、电子设备和存储介质 |
CN110516050A (zh) * | 2019-07-15 | 2019-11-29 | 上海文思海辉金信软件有限公司 | 一种基于知识图谱的多路径训练场景的构建方法 |
CN110797026A (zh) * | 2019-09-17 | 2020-02-14 | 腾讯科技(深圳)有限公司 | 一种语音识别方法、装置及存储介质 |
CN111179916B (zh) * | 2019-12-31 | 2023-10-13 | 广州市百果园信息技术有限公司 | 重打分模型训练方法、语音识别方法及相关装置 |
CN111145733B (zh) * | 2020-01-03 | 2023-02-28 | 深圳追一科技有限公司 | 语音识别方法、装置、计算机设备和计算机可读存储介质 |
CN111274801A (zh) * | 2020-02-25 | 2020-06-12 | 苏州跃盟信息科技有限公司 | 分词方法及装置 |
CN111916058A (zh) * | 2020-06-24 | 2020-11-10 | 西安交通大学 | 一种基于增量词图重打分的语音识别方法及*** |
CN111998869B (zh) * | 2020-09-29 | 2021-05-04 | 北京嘀嘀无限科技发展有限公司 | 路线生成方法、装置、电子设备和计算机可读存储介质 |
CN112102815B (zh) * | 2020-11-13 | 2021-07-13 | 深圳追一科技有限公司 | 语音识别方法、装置、计算机设备和存储介质 |
CN112885336B (zh) * | 2021-01-29 | 2024-02-02 | 深圳前海微众银行股份有限公司 | 语音识别***的训练、识别方法、装置、电子设备 |
CN113487024A (zh) * | 2021-06-29 | 2021-10-08 | 任立椋 | 交替序列生成模型训练方法、从文本中抽取图的方法 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101645270A (zh) * | 2008-12-12 | 2010-02-10 | 中国科学院声学研究所 | 一种双向语音识别处理***及方法 |
CN101740024A (zh) * | 2008-11-19 | 2010-06-16 | 中国科学院自动化研究所 | 基于广义流利的口语流利度自动评估方法 |
CN105513589A (zh) * | 2015-12-18 | 2016-04-20 | 百度在线网络技术(北京)有限公司 | 语音识别方法和装置 |
CN105681920A (zh) * | 2015-12-30 | 2016-06-15 | 深圳市鹰硕音频科技有限公司 | 一种具有语音识别功能的网络教学方法及*** |
CN106803422A (zh) * | 2015-11-26 | 2017-06-06 | 中国科学院声学研究所 | 一种基于长短时记忆网络的语言模型重估方法 |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7219058B1 (en) * | 2000-10-13 | 2007-05-15 | At&T Corp. | System and method for processing speech recognition results |
CN1499484A (zh) * | 2002-11-06 | 2004-05-26 | 北京天朗语音科技有限公司 | 汉语连续语音识别*** |
US7464031B2 (en) * | 2003-11-28 | 2008-12-09 | International Business Machines Corporation | Speech recognition utilizing multitude of speech features |
US7848917B2 (en) * | 2006-03-30 | 2010-12-07 | Microsoft Corporation | Common word graph based multimodal input |
CN101647021B (zh) * | 2007-04-13 | 2013-03-27 | 麻省理工学院 | 语音数据检索装置、语音数据检索方法、语音数据检索程序和包含有语音数据检索程序的计算机可用介质 |
TWI441163B (zh) * | 2011-05-10 | 2014-06-11 | Univ Nat Chiao Tung | 中文語音辨識裝置及其辨識方法 |
CN106856092B (zh) * | 2015-12-09 | 2019-11-15 | 中国科学院声学研究所 | 基于前向神经网络语言模型的汉语语音关键词检索方法 |
-
2018
- 2018-01-19 CN CN201810054749.2A patent/CN108415898B/zh active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101740024A (zh) * | 2008-11-19 | 2010-06-16 | 中国科学院自动化研究所 | 基于广义流利的口语流利度自动评估方法 |
CN101645270A (zh) * | 2008-12-12 | 2010-02-10 | 中国科学院声学研究所 | 一种双向语音识别处理***及方法 |
CN106803422A (zh) * | 2015-11-26 | 2017-06-06 | 中国科学院声学研究所 | 一种基于长短时记忆网络的语言模型重估方法 |
CN105513589A (zh) * | 2015-12-18 | 2016-04-20 | 百度在线网络技术(北京)有限公司 | 语音识别方法和装置 |
CN105681920A (zh) * | 2015-12-30 | 2016-06-15 | 深圳市鹰硕音频科技有限公司 | 一种具有语音识别功能的网络教学方法及*** |
Non-Patent Citations (6)
Title |
---|
LATTICE RESCORING STRATEGIES FOR LONG SHORT TERM MEMORY LANGUAGE MODELS IN SPEECH RECOGNITION;Shankar Kumar等;《https://arxiv.org/abs/1711.05448v1》;20151115;1-8 * |
zhehuai chen等;A Unifified Confifidence Measure Framework Using Auxiliary Norma;《Conference: International Conference on Intelligent Science and Big Data Engineering》;20171223;123-133 * |
基于加权有限状态机的动态匹配词图生成算法;郭宇弘等;《电子与信息学报》;20140115;第36卷(第1期);140-146 * |
电话交谈语音识别中基于LSTM-DNN 语言模型的重评估方法研究;左玲云等;《重庆邮电大学学报》;20160415;第28卷(第2期);180-186,193 * |
连续语音识别中的循环神经网络语言模型技术研究;张剑;《中国优秀硕士学位论文全文数据库 信息科技辑》;20160715;I136-95 * |
连续语音识别解码技术的研究;尹明明;《中国优秀硕士学位论文全文数据库 信息科技辑》;20120715;I136-313 * |
Also Published As
Publication number | Publication date |
---|---|
CN108415898A (zh) | 2018-08-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108415898B (zh) | 深度学习语言模型的词图重打分方法和*** | |
Higuchi et al. | Improved Mask-CTC for non-autoregressive end-to-end ASR | |
US20050159952A1 (en) | Pattern matching for large vocabulary speech recognition with packed distribution and localized trellis access | |
EP0527650B1 (en) | Speech recognition apparatus | |
US9336771B2 (en) | Speech recognition using non-parametric models | |
JP2775140B2 (ja) | パターン認識方法、音声認識方法および音声認識装置 | |
EP1133766B1 (en) | Network and language models for use in a speech recognition system | |
CN112287670A (zh) | 文本纠错方法、***、计算机设备及可读存储介质 | |
US7031915B2 (en) | Assisted speech recognition by dual search acceleration technique | |
CN1156820C (zh) | 使用词汇树的识别*** | |
US20210365723A1 (en) | Position Masking for Transformer Models | |
CN112380841B (zh) | 一种中文拼写纠错方法、装置、计算机设备及存储介质 | |
Li et al. | A parallelizable lattice rescoring strategy with neural language models | |
Zamora-Martinez et al. | N-gram-based machine translation enhanced with neural networks for the French-English BTEC-IWSLT'10 task. | |
US20040148169A1 (en) | Speech recognition with shadow modeling | |
US20220067280A1 (en) | Multi-token embedding and classifier for masked language models | |
US20220027719A1 (en) | Compressing tokens based on positions for transformer models | |
Khassanov et al. | Enriching rare word representations in neural language models by embedding matrix augmentation | |
US11954448B2 (en) | Determining position values for transformer models | |
CN111078886B (zh) | 基于dmcnn的特殊事件提取*** | |
Biadsy et al. | Backoff inspired features for maximum entropy language models | |
KR20230156425A (ko) | 자체 정렬을 통한 스트리밍 asr 모델 지연 감소 | |
CN110992939B (zh) | 语言模型训练方法、解码方法、装置、存储介质及设备 | |
CN110110294B (zh) | 一种动态反向解码的方法、装置及可读存储介质 | |
Paul | The Lincoln large-vocabulary stack-decoder based HMM CSR |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200622 Address after: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Applicant after: AI SPEECH Co.,Ltd. Applicant after: Shanghai Jiaotong University Intellectual Property Management Co.,Ltd. Address before: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Applicant before: AI SPEECH Co.,Ltd. Applicant before: SHANGHAI JIAO TONG University |
|
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20201027 Address after: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Applicant after: AI SPEECH Co.,Ltd. Address before: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Applicant before: AI SPEECH Co.,Ltd. Applicant before: Shanghai Jiaotong University Intellectual Property Management Co.,Ltd. |
|
CB02 | Change of applicant information |
Address after: 215123 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou City, Jiangsu Province Applicant after: Sipic Technology Co.,Ltd. Address before: 215123 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou City, Jiangsu Province Applicant before: AI SPEECH Co.,Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Word Graph Re scoring Method and System for Deep Learning Language Models Effective date of registration: 20230726 Granted publication date: 20210924 Pledgee: CITIC Bank Limited by Share Ltd. Suzhou branch Pledgor: Sipic Technology Co.,Ltd. Registration number: Y2023980049433 |
|
PE01 | Entry into force of the registration of the contract for pledge of patent right |